avatar

Shan Yu

Ph.D. Student
UCLA
shanyu (at) cs.ucla.edu


About Me

I am a third-year Ph.D. student in Computer Science at UCLA, where I am fortunate to be advised by Prof. Harry Xu.

My research focuses on machine learning systems, where I design and build high-performance, cost-effective solutions by leveraging application semantics. My current work includes developing scalable and efficient systems for large language model (LLM) serving (Prism, ConServe) and video querying (VQPy).

Before my PhD, I spent four years at Intel as an AI frameworks engineer, building open-source big data and AI systems optimized for Intel CPUs in data centers.

Publications

  1. Prism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving
    Shan Yu, Jiarong Xing, Yifan Qiao, Mingyuan Ma, Yangmin Li, Yang Wang, Shuo Yang, Zhiqiang Xie, Shiyi Cao, Ke Bao, Ion Stoica, Harry Xu, Ying Sheng
    arXiv preprint, 2025
    PDF Code
  2. ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving
    Yifan Qiao, Shu Anzai, Shan Yu, Haoran Ma, Yang Wang, Miryung Kim, Harry Xu
    arXiv preprint, 2024
    PDF Code
  3. VQPy: An Object-Oriented Approach to Modern Video Analytics
    Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, Harry Xu
    Conference on Machine Learning and Systems (MLSys), 2024.
    PDF Code
  4. DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency
    Haoran Ma, Yifan Qiao, Shi Liu, Shan Yu, Yuanjiang Ni, Qingda Lu, Jiesheng Wu, Yiying Zhang, Miryung Kim, Harry Xu
    USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2024.
    PDF Code Talk
  5. Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding and Contextual Label Affinity
    Hugo Latapie, Shan Yu, Patrick Hammer, Kristinn R. Thorisson, Vahagn Petrosyan, Brandon Kynoch, Alind Khare, Payman Behnam, Alexey Tumanov, Aksheit Saxena, Anish Aralikatti, Hanning Chen, Mohsen Imani, Mike Archbold, Tangrui Li, Pei Wang, Justin Hart
    arXiv preprint, 2023
    PDF
  6. BigDL 2.0: Seamless scaling of ai pipelines from laptops to distributed cluster
    Jason (Jinquan) Dai, Ding Ding, Dongjie Shi, Shengsheng Huang, Jiao Wang, Xin Qiu, Kai Huang, Guoqiong Song, Yang Wang, Qiyuan Gong, Jiaming Song, Shan Yu, Le Zheng, Yina Chen, Junwei Deng, Ge Song
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2022.
    PDF Code

Services

Artifact Evaluation Committee

Talks

VQPy: An Object-Oriented Approach to Modern Video Analytics

What's on-going in Spark + AI Community

Chronos: Scalable Time Series Analytics with AutoML

Time Series Analytics using AutoML and Ray on Analytics Zoo

Leveraging Distributed AutoML for Time Series Analytics

Game Playing Using AI on Spark

Awards